Triple

T26896994
Position Surface form Disambiguated ID Type / Status
Subject Arendelle Castle E677921 entity
Predicate inspiredByRealLocation P113256 FINISHED
Object Akershus Fortress, Oslo NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Akershus Fortress, Oslo | Statement: [Arendelle Castle, inspiredByRealLocation, Akershus Fortress, Oslo]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: inspiredByRealLocation
Context triple: [Arendelle Castle, inspiredByRealLocation, Akershus Fortress, Oslo]
  • A. inspiredByPlace
    Indicates that something (such as a work, idea, or creation) originates from or is significantly influenced by a particular location or environment.
  • B. portrayedByRealWorldLocation chosen
    Indicates that a fictional or represented location is depicted or substituted by an actual real-world location.
  • C. inspiredByRealStreet
    Indicates that something is based on, modeled after, or creatively derived from an actual, existing street in the real world.
  • D. basedInFictionalLocation
    Indicates that an entity’s primary setting, origin, or operations occur in a fictional (non-real) location.
  • E. fictionalLocationAssociatedWith
    Indicates a relationship where a fictional entity (such as a character, event, or work) is connected to or set in a particular fictional location.
  • F. None of above.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69eee9befee48190a26f214faa867be7 completed April 27, 2026, 4:44 a.m.
NER Named-entity recognition batch_69f65aa07c048190a5df30d53d8f0cf5 completed May 2, 2026, 8:12 p.m.
PD Predicate disambiguation batch_69f659cc571c819097e51e531961d812 completed May 2, 2026, 8:08 p.m.
Created at: April 27, 2026, 5:48 a.m.